在多线程应用程序中设置硬件断点不会触发

Setting a hardwarebreakpoint in multithreaded application doesn't fire

我写了一个小调试器来分析和查找某些问题。现在我实现了一个硬件断点来检测被覆盖的内存地址的访问。当我 运行 我的调试器带有测试过程时,一切正常。当我访问该地址时,断点将触发并记录调用堆栈。问题是,当我 运行 对一个应用程序 运行 宁多个线程时。我正在将断点复制到创建的每个线程以及主线程中。 None 个函数报告错误,一切看起来都很好,但是当访问该地址时,断点永远不会触发。

所以我想知道是否有一些文档对此进行了描述,或者在多线程应用程序的情况下是否还有其他我必须做的事情。

设置断点的函数是这样的:

#ifndef _HARDWARE_BREAKPOINT_H
#define _HARDWARE_BREAKPOINT_H

#include "breakpoint.h"

#define MAX_HARDWARE_BREAKPOINT     4

#define REG_DR0_BIT                 1
#define REG_DR1_BIT                 4
#define REG_DR2_BIT                 16
#define REG_DR3_BIT                 64


class HardwareBreakpoint : public Breakpoint
{
public:
    typedef enum 
    {
        REG_INVALID     = -1,
        REG_DR0         =  0,
        REG_DR1         =  1,
        REG_DR2         =  2,
        REG_DR3         =  3
    } Register;

    typedef enum
    {
        CODE,
        READWRITE,
        WRITE,
    } Type;

    typedef enum
    {
        SIZE_1,
        SIZE_2,
        SIZE_4,
        SIZE_8,
    } Size;

    typedef struct 
    {
        void *pAddress;
        bool bBusy;
        Type nType;
        Size nSize;
        Register nRegister;
    } Info;

public:
    HardwareBreakpoint(HANDLE hThread);
    virtual ~HardwareBreakpoint(void);

    /**
     * Sets a hardware breakpoint. If no register is free or an error occured
     * REG_INVALID is returned, otherwise the hardware register for the given breakpoint.
     */
    HardwareBreakpoint::Register set(void *pAddress, Type nType, Size nSize);
    void remove(void *pAddress);
    void remove(Register nRegister);

    inline Info const *getInfo(Register nRegister) const { return &mBreakpoint[nRegister]; }

private:
    typedef Breakpoint super;

private:
    Info mBreakpoint[MAX_HARDWARE_BREAKPOINT];
    size_t mRegBit[MAX_HARDWARE_BREAKPOINT];
    size_t mRegOffset[MAX_HARDWARE_BREAKPOINT];
};
#endif // _HARDWARE_BREAKPOINT_H

void SetBits(DWORD_PTR &dw, size_t lowBit, size_t bits, size_t newValue)
{
    DWORD_PTR mask = (1 << bits) - 1; 
    dw = (dw & ~(mask << lowBit)) | (newValue << lowBit);
}

HardwareBreakpoint::HardwareBreakpoint(HANDLE hThread)
    : super(hThread)
{
    mRegBit[REG_DR0] = REG_DR0_BIT;
    mRegBit[REG_DR1] = REG_DR1_BIT;
    mRegBit[REG_DR2] = REG_DR2_BIT;
    mRegBit[REG_DR3] = REG_DR3_BIT;

    CONTEXT ct;
    mRegOffset[REG_DR0] = reinterpret_cast<size_t>(&ct.Dr0) - reinterpret_cast<size_t>(&ct);
    mRegOffset[REG_DR1] = reinterpret_cast<size_t>(&ct.Dr1) - reinterpret_cast<size_t>(&ct);
    mRegOffset[REG_DR2] = reinterpret_cast<size_t>(&ct.Dr2) - reinterpret_cast<size_t>(&ct);
    mRegOffset[REG_DR3] = reinterpret_cast<size_t>(&ct.Dr3) - reinterpret_cast<size_t>(&ct);

    memset(&mBreakpoint[0], 0, sizeof(mBreakpoint));
    for(int i = 0; i < MAX_HARDWARE_BREAKPOINT; i++)
        mBreakpoint[i].nRegister = (Register)i;
}

HardwareBreakpoint::Register HardwareBreakpoint::set(void *pAddress, Type nType, Size nSize)
{
    CONTEXT ct = {0};
    super::setAddress(pAddress);

    ct.ContextFlags = CONTEXT_DEBUG_REGISTERS;
    if(!GetThreadContext(getThread(), &ct))
        return HardwareBreakpoint::REG_INVALID;

    size_t iReg = 0;
    for(int i = 0; i < MAX_HARDWARE_BREAKPOINT; i++)
    {
        if (ct.Dr7 & mRegBit[i])
            mBreakpoint[i].bBusy = true;
        else
            mBreakpoint[i].bBusy = false;
    }

    Info *reg = NULL;

    // Address already used?
    for(int i = 0; i < MAX_HARDWARE_BREAKPOINT; i++)
    {
        if(mBreakpoint[i].pAddress == pAddress)
        {
            iReg = i;
            reg = &mBreakpoint[i];
            break;
        }
    }

    if(reg == NULL)
    {
        for(int i = 0; i < MAX_HARDWARE_BREAKPOINT; i++)
        {
            if(!mBreakpoint[i].bBusy)
            {
                iReg = i;
                reg = &mBreakpoint[i];
                break;
            }
        }
    }

    // No free register available
    if(!reg)
        return HardwareBreakpoint::REG_INVALID;

    *(void **)(((char *)&ct)+mRegOffset[iReg]) = pAddress;
    reg->bBusy = true;

    ct.Dr6 = 0;
    int st = 0;
    if (nType == CODE)
        st = 0;
    if (nType == READWRITE)
        st = 3;
    if (nType == WRITE)
        st = 1;

    int le = 0;
    if (nSize == SIZE_1)
        le = 0;
    else if (nSize == SIZE_2)
        le = 1;
    else if (nSize == SIZE_4)
        le = 3;
    else if (nSize == SIZE_8)
        le = 2;

    SetBits(ct.Dr7, 16 + iReg*4, 2, st);
    SetBits(ct.Dr7, 18 + iReg*4, 2, le);
    SetBits(ct.Dr7, iReg*2, 1, 1);

    ct.ContextFlags = CONTEXT_DEBUG_REGISTERS;
    if(!SetThreadContext(getThread(), &ct))
        return REG_INVALID;

    return reg->nRegister;
}

每当创建新线程时,我都会在主调试器循环中设置断点 CREATE_THREAD_DEBUG_EVENT 但是查看 GDB 的源代码似乎没有在那里完成,所以也许就是这样要早?

所以我终于找到了这个问题的答案。

在调试事件循环中,我正在监视 windows 发送给我的事件。其中一个事件是 CREATE_THREAD_DEBUG_EVENT,每当创建新线程时我都会设置硬件断点。

问题是,此事件的通知是在线程实际启动之前发出的。所以 Windows 是在发送此事件后第一次设置上下文,这当然会覆盖我之前设置的任何上下文数据。

我现在的解决方案是,当CREATE_THREAD_DEBUG_EVENT出现时,我在线程的起始地址下了一个软件断点,这样第一条指令就是我的断点。当我收到断点事件时,我恢复了原始代码并安装了硬件断点,现在可以正常触发了。

如果有更好的解决方案,我洗耳恭听。 :)